MapReduce版Wordcount的书写

主方法:

package com.bjsxt.sn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import com.sun.jersey.core.impl.provider.entity.XMLJAXBElementProvider.Text;

public class TestMapReduce {
	public static void main(String[] args) throws Exception {
		Configuration conf=new Configuration();
		Job job=Job.getInstance(conf);
		job.setJarByClass(TestMapReduce.class);
		job.setJobName("ooxx");
		Path fileIn=new Path("/user/root/test.txt");
		FileInputFormat.addInputPath(job, fileIn);
		
		Path fileout=new Path("/data/wc/output01");
		if(fileout.getFileSystem(conf).exists(fileout)) {
			fileout.getFileSystem(conf).delete(fileout,true);
		}
		
		FileOutputFormat.setOutputPath(job, fileout);
		
		job.setMapperClass(MyMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setReducerClass(Reducer.class);
		job.waitForCompletion(true);
		
	}
}

map方法:

package com.bjsxt.sn;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class MyMapper extends Mapper<Object, Text, Text, IntWritable>{
	private final static IntWritable one=new IntWritable(1);
	private Text word=new Text();
	public void map(Object key,Text value,Context context) throws IOException, InterruptedException {
		StringTokenizer itr=new StringTokenizer(value.toString());
		while(itr.hasMoreTokens()) {
			word.set(itr.nextToken());
			
			context.write(word, one);
		}	
	}
}

reduce方法:

package com.bjsxt.sn;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;

public class Reducer extends org.apache.hadoop.mapreduce.Reducer<Text, IntWritable, Text, IntWritable>{
	IntWritable result=new IntWritable();
	public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
		int sum=0;
		for (IntWritable val : values) {
			sum +=val.get();
		}
		Iterator<IntWritable> it=values.iterator();
		
		while(it.hasNext()) {
			IntWritable n=it.next();
			System.out.println(n);
			System.out.println(key);
		}
		result.set(sum);
		context.write(key, result);		
	}
}

提交命令:

查看:

 

猜你喜欢

转载自blog.csdn.net/wyqwilliam/article/details/82490736
今日推荐